PermaTrackPr: Learning to Track with Object Permanence
MOT17-06-DPM
Benchmark:
MOT17 |
Short name:
PermaTrackPr
Detector:
Private
Description:
This is a variant of our model evaluated with private detections.
Reference:
P. Tokmakov, J. Li, W. Burgard, A. Gaidon. Learning to Track with Object Permanence. In ICCV, 2021.
Last submitted:
June 12, 2021 (2 years ago)
Published:
June 16, 2021 at 01:27:37 CET
Submissions:
1
Project page / code:
n/a
Open source:
No
Hardware:
Tesla V100
Runtime:
11.9 Hz
Benchmark performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT17 | 73.8 | 68.9 | 55.5 | 1,032 (43.8) | 405 (17.2) | 28,998 | 115,104 | 79.6 | 93.9 | 53.1 | 58.5 | 59.8 | 70.1 | 63.9 | 75.4 | 81.4 | 1.6 | 3,699 (0.0) | 6,132 (0.0) |
Detailed performance:
| Sequence | MOTA | IDF1 | HOTA | MT | ML | FP | FN | Rcll | Prcn | AssA | DetA | AssRe | AssPr | DetRe | DetPr | LocA | FAF | ID Sw. | Frag |
| MOT17-01-DPM | 50.9 | 48.2 | 39.2 | 13 | 8 | 831 | 2,303 | 64.3 | 83.3 | 35.9 | 43.0 | 43.2 | 59.7 | 50.1 | 64.9 | 79.9 | 1.8 | 32 | 62 |
| MOT17-01-FRCNN | 50.9 | 48.2 | 39.2 | 13 | 8 | 831 | 2,303 | 64.3 | 83.3 | 35.9 | 43.0 | 43.2 | 59.7 | 50.1 | 64.9 | 79.9 | 1.8 | 32 | 62 |
| MOT17-01-SDP | 50.9 | 48.2 | 39.2 | 13 | 8 | 831 | 2,303 | 64.3 | 83.3 | 35.9 | 43.0 | 43.2 | 59.7 | 50.1 | 64.9 | 79.9 | 1.8 | 32 | 62 |
| MOT17-03-DPM | 89.5 | 82.7 | 64.9 | 133 | 1 | 2,299 | 8,587 | 91.8 | 97.7 | 61.6 | 68.9 | 67.4 | 75.8 | 73.3 | 78.0 | 81.2 | 1.5 | 141 | 401 |
| MOT17-03-FRCNN | 89.5 | 82.7 | 64.9 | 133 | 1 | 2,299 | 8,587 | 91.8 | 97.7 | 61.6 | 68.9 | 67.4 | 75.8 | 73.3 | 78.0 | 81.2 | 1.5 | 141 | 401 |
| MOT17-03-SDP | 89.5 | 82.7 | 64.9 | 133 | 1 | 2,299 | 8,587 | 91.8 | 97.7 | 61.6 | 68.9 | 67.4 | 75.8 | 73.3 | 78.0 | 81.2 | 1.5 | 141 | 401 |
| MOT17-06-DPM | 61.1 | 48.0 | 39.4 | 82 | 44 | 707 | 3,655 | 69.0 | 92.0 | 31.3 | 50.3 | 49.8 | 44.8 | 55.1 | 73.5 | 81.0 | 0.6 | 220 | 302 |
| MOT17-06-FRCNN | 61.1 | 48.0 | 39.4 | 82 | 44 | 707 | 3,655 | 69.0 | 92.0 | 31.3 | 50.3 | 49.8 | 44.8 | 55.1 | 73.5 | 81.0 | 0.6 | 220 | 302 |
| MOT17-06-SDP | 61.1 | 48.0 | 39.4 | 82 | 44 | 707 | 3,655 | 69.0 | 92.0 | 31.3 | 50.3 | 49.8 | 44.8 | 55.1 | 73.5 | 81.0 | 0.6 | 220 | 302 |
| MOT17-07-DPM | 59.8 | 47.3 | 40.4 | 26 | 4 | 2,192 | 4,363 | 74.2 | 85.1 | 33.5 | 50.2 | 39.0 | 59.2 | 58.6 | 67.2 | 80.1 | 4.4 | 240 | 385 |
| MOT17-07-FRCNN | 59.8 | 47.3 | 40.4 | 26 | 4 | 2,192 | 4,363 | 74.2 | 85.1 | 33.5 | 50.2 | 39.0 | 59.2 | 58.6 | 67.2 | 80.1 | 4.4 | 240 | 385 |
| MOT17-07-SDP | 59.8 | 47.3 | 40.4 | 26 | 4 | 2,192 | 4,363 | 74.2 | 85.1 | 33.5 | 50.2 | 39.0 | 59.2 | 58.6 | 67.2 | 80.1 | 4.4 | 240 | 385 |
| MOT17-08-DPM | 51.2 | 46.1 | 39.8 | 24 | 15 | 856 | 9,255 | 56.2 | 93.3 | 37.1 | 43.6 | 43.8 | 60.8 | 46.7 | 77.5 | 83.4 | 1.4 | 188 | 268 |
| MOT17-08-FRCNN | 51.2 | 46.1 | 39.8 | 24 | 15 | 856 | 9,255 | 56.2 | 93.3 | 37.1 | 43.6 | 43.8 | 60.8 | 46.7 | 77.5 | 83.4 | 1.4 | 188 | 268 |
| MOT17-08-SDP | 51.2 | 46.1 | 39.8 | 24 | 15 | 856 | 9,255 | 56.2 | 93.3 | 37.1 | 43.6 | 43.8 | 60.8 | 46.7 | 77.5 | 83.4 | 1.4 | 188 | 268 |
| MOT17-12-DPM | 46.7 | 57.2 | 49.3 | 27 | 28 | 1,517 | 3,065 | 64.6 | 78.7 | 53.3 | 45.8 | 63.1 | 70.8 | 55.3 | 67.3 | 85.5 | 1.7 | 41 | 77 |
| MOT17-12-FRCNN | 46.7 | 57.2 | 49.3 | 27 | 28 | 1,517 | 3,065 | 64.6 | 78.7 | 53.3 | 45.8 | 63.1 | 70.8 | 55.3 | 67.3 | 85.5 | 1.7 | 41 | 77 |
| MOT17-12-SDP | 46.7 | 57.2 | 49.3 | 27 | 28 | 1,517 | 3,065 | 64.6 | 78.7 | 53.3 | 45.8 | 63.1 | 70.8 | 55.3 | 67.3 | 85.5 | 1.7 | 41 | 77 |
| MOT17-14-DPM | 52.5 | 52.5 | 40.9 | 39 | 35 | 1,264 | 7,140 | 61.4 | 90.0 | 37.7 | 44.7 | 43.0 | 61.6 | 49.2 | 72.2 | 81.2 | 1.7 | 371 | 549 |
| MOT17-14-FRCNN | 52.5 | 52.5 | 40.9 | 39 | 35 | 1,264 | 7,140 | 61.4 | 90.0 | 37.7 | 44.7 | 43.0 | 61.6 | 49.2 | 72.2 | 81.2 | 1.7 | 371 | 549 |
| MOT17-14-SDP | 52.5 | 52.5 | 40.9 | 39 | 35 | 1,264 | 7,140 | 61.4 | 90.0 | 37.7 | 44.7 | 43.0 | 61.6 | 49.2 | 72.2 | 81.2 | 1.7 | 371 | 549 |
Raw data:
